mlsanityData to 13 Oct 2026

Curriculum Learning of Multiple Tasks

arXiv 1412.1353 ↗First posted 3 Dec 2014stat.ML cs.LGcited by 65

Not on the map. Why?

Abstract (arXiv)

Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover the favourable order of tasks.

Key facts. Cited by 65 papers in the map (data through 13 Oct 2026). First posted on arXiv 3 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 10; 2022: 13; 2023: 14; 2024: 5; 2025: 14; 2026: 9.

65 papers.

Sort:

By area:

  1. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 539
  2. 2021Curriculum Learning: A Surveycited by 257
  3. 2025Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learningcited by 71
  4. 2021Uncertainty-Aware Unsupervised Domain Adaptation in Object Detectioncited by 59
  5. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoningcited by 39
  6. 2023Continual Learning in Linear Classification on Separable Datacited by 33
  7. 2022The Effect of Task Ordering in Continual Learningcited by 30
  8. 2021An Analytical Theory of Curriculum Learning in Teacher-Student Networkscited by 27
  9. 2023ASP: Learn a Universal Neural Solver!cited by 27
  10. 2024Denoising Task Difficulty-based Curriculum for Training Diffusion Modelscited by 26
  11. 2023Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputscited by 22
  12. 2021Medical Image Segmentation with Limited Supervision: A Review of Deep Network Modelscited by 21
38 more
  1. 2021Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absentcited by 21
  2. 2023CL-MAE: Curriculum-Learned Masked Autoencoderscited by 21
  3. 2024CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Modelscited by 20
  4. 2023Domain Generalization via Balancing Training Difficulty and Model Capabilitycited by 19
  5. 2025Optimal Task Order for Continual Learning of Multiple Taskscited by 14
  6. 2025RecGPT Technical Reportcited by 11
  7. 2023Traffic-Domain Video Question Answering with Automatic Captioningcited by 10
  8. 2021Coarse-to-Fine Curriculum Learningcited by 9
  9. 2022Learning Rate Curriculumcited by 9
  10. 2022When Do Curricula Work in Federated Learning?cited by 9
  11. 2026From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detectioncited by 9
  12. 2022Let the Model Decide its Curriculum for Multitask Learningcited by 8
  13. 2022MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequencescited by 8
  14. 2022Curriculum-based Asymmetric Multi-task Reinforcement Learningcited by 8
  15. 2023RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learningcited by 8
  16. 2021How to distribute data across tasks for meta-learning?cited by 7
  17. 2023Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillationcited by 7
  18. 2023Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimizationcited by 6
  19. 2022Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agentscited by 5
  20. 2022CRISP: Curriculum based Sequential Neural Decoders for Polar Code Familycited by 5
  21. 2026Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotioncited by 5
  22. 2022PInKS: Preconditioned Commonsense Inference with Minimal Supervisioncited by 4
  23. 2025RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoningcited by 4
  24. 2023DCLP: Neural Architecture Predictor with Curriculum Contrastive Learningcited by 3
  25. 2024CBM: Curriculum by Maskingcited by 3
  26. 2025A statistical physics framework for optimal learningcited by 3
  27. 2025Heterogeneous Adversarial Play in Interactive Environmentscited by 3
  28. 2022InDistill: Information flow-preserving knowledge distillation for model compressioncited by 2
  29. 2022Task Phasing: Automated Curriculum Learning from Demonstrationscited by 2
  30. 2022LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learningcited by 2
  31. 2023Confidence-Aware Calibration and Scoring Functions for Curriculum Learningcited by 2
  32. 2026Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledgecited by 2
  33. 2021Object Localization Through a Single Multiple-Model Convolutional Neural Network with a Specific Training Approachcited by 1
  34. 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skillscited by 1
  35. 2024Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Taskscited by 1
  36. 2025RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generationcited by 1
  37. 2025CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learningcited by 1
  38. 2025STCL:Curriculum learning Strategies for deep learning image steganography modelscited by 1

50 most cited of 65 All 65 (JSON)